public virtual IPreferenceArray GetPreferencesForItem(long itemID)
{
if (tempPrefs == null)
{
return(_delegate.GetPreferencesForItem(itemID));
}
IPreferenceArray delegatePrefs = null;
try {
delegatePrefs = _delegate.GetPreferencesForItem(itemID);
} catch (NoSuchItemException nsie) {
// OK. Probably an item that only the anonymous user has
//if (log.isDebugEnabled()) {
log.Debug("Item {} unknown", itemID);
//}
}
for (int i = 0; i < tempPrefs.Length(); i++)
{
if (tempPrefs.GetItemID(i) == itemID)
{
return(cloneAndMergeInto(delegatePrefs, itemID, tempPrefs.GetUserID(i), tempPrefs.GetValue(i)));
}
}
if (delegatePrefs == null)
{
// No, didn't find it among the anonymous user prefs
throw new NoSuchItemException(itemID);
}
return(delegatePrefs);
}
public double averateRating(long itemID)
{
IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID);
IRunningAverage avg = new FullRunningAverage();
foreach (IPreference pref in prefs)
{
avg.AddDatum(pref.GetValue());
}
return(avg.GetAverage());
}
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) {
FastIDSet possibleItemsIDs = new FastIDSet();
foreach (long itemID in preferredItemIDs) {
IPreferenceArray itemPreferences = dataModel.GetPreferencesForItem(itemID);
int numUsersPreferringItem = itemPreferences.Length();
for (int index = 0; index < numUsersPreferringItem; index++) {
possibleItemsIDs.AddAll(dataModel.GetItemIDsFromUser(itemPreferences.GetUserID(index)));
}
}
possibleItemsIDs.RemoveAll(preferredItemIDs);
return possibleItemsIDs;
}
public void testPreferencesForItem()
{
IPreferenceArray prefs = model.GetPreferencesForItem(456);
Assert.NotNull(prefs);
IPreference pref1 = prefs.Get(0);
Assert.AreEqual(123, pref1.GetUserID());
Assert.AreEqual(456, pref1.GetItemID());
IPreference pref2 = prefs.Get(1);
Assert.AreEqual(456, pref2.GetUserID());
Assert.AreEqual(456, pref2.GetItemID());
Assert.AreEqual(2, prefs.Length());
}
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel)
{
FastIDSet possibleItemsIDs = new FastIDSet();
foreach (long itemID in preferredItemIDs)
{
IPreferenceArray itemPreferences = dataModel.GetPreferencesForItem(itemID);
int numUsersPreferringItem = itemPreferences.Length();
for (int index = 0; index < numUsersPreferringItem; index++)
{
possibleItemsIDs.AddAll(dataModel.GetItemIDsFromUser(itemPreferences.GetUserID(index)));
}
}
possibleItemsIDs.RemoveAll(preferredItemIDs);
return(possibleItemsIDs);
}
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel)
{
var preferredItemIDsIterator = ((IEnumerable <long>)preferredItemIDs).GetEnumerator();
if (preferredItemIDs.Length > maxItems)
{
double samplingRate = (double)maxItems / preferredItemIDs.Length;
log.Info("preferredItemIDs.Length {0}, samplingRate {1}", preferredItemIDs.Length, samplingRate);
preferredItemIDsIterator =
new SamplinglongPrimitiveIterator(preferredItemIDsIterator, samplingRate);
}
FastIDSet possibleItemsIDs = new FastIDSet();
while (preferredItemIDsIterator.MoveNext())
{
long itemID = preferredItemIDsIterator.Current;
IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID);
int prefsLength = prefs.Length();
if (prefsLength > maxUsersPerItem)
{
var sampledPrefs =
new FixedSizeSamplingIterator <IPreference>(maxUsersPerItem, prefs.GetEnumerator());
while (sampledPrefs.MoveNext())
{
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(sampledPrefs.Current.GetUserID()));
}
}
else
{
for (int i = 0; i < prefsLength; i++)
{
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(prefs.GetUserID(i)));
}
}
}
possibleItemsIDs.RemoveAll(preferredItemIDs);
return(possibleItemsIDs);
}
public override double ItemSimilarity(long itemID1, long itemID2)
{
IDataModel dataModel = getDataModel();
IPreferenceArray xPrefs = dataModel.GetPreferencesForItem(itemID1);
IPreferenceArray yPrefs = dataModel.GetPreferencesForItem(itemID2);
int xLength = xPrefs.Length();
int yLength = yPrefs.Length();
if (xLength == 0 || yLength == 0)
{
return(Double.NaN);
}
long xIndex = xPrefs.GetUserID(0);
long yIndex = yPrefs.GetUserID(0);
int xPrefIndex = 0;
int yPrefIndex = 0;
double sumX = 0.0;
double sumX2 = 0.0;
double sumY = 0.0;
double sumY2 = 0.0;
double sumXY = 0.0;
double sumXYdiff2 = 0.0;
int count = 0;
// No, pref inferrers and transforms don't apply here. I think.
while (true)
{
int compare = xIndex <yIndex ? -1 : xIndex> yIndex ? 1 : 0;
if (compare == 0)
{
// Both users expressed a preference for the item
double x = xPrefs.GetValue(xPrefIndex);
double y = yPrefs.GetValue(yPrefIndex);
sumXY += x * y;
sumX += x;
sumX2 += x * x;
sumY += y;
sumY2 += y * y;
double diff = x - y;
sumXYdiff2 += diff * diff;
count++;
}
if (compare <= 0)
{
if (++xPrefIndex == xLength)
{
break;
}
xIndex = xPrefs.GetUserID(xPrefIndex);
}
if (compare >= 0)
{
if (++yPrefIndex == yLength)
{
break;
}
yIndex = yPrefs.GetUserID(yPrefIndex);
}
}
double result;
if (centerData)
{
// See comments above on these computations
double n = (double)count;
double meanX = sumX / n;
double meanY = sumY / n;
// double centeredSumXY = sumXY - meanY * sumX - meanX * sumY + n * meanX * meanY;
double centeredSumXY = sumXY - meanY * sumX;
// double centeredSumX2 = sumX2 - 2.0 * meanX * sumX + n * meanX * meanX;
double centeredSumX2 = sumX2 - meanX * sumX;
// double centeredSumY2 = sumY2 - 2.0 * meanY * sumY + n * meanY * meanY;
double centeredSumY2 = sumY2 - meanY * sumY;
result = computeResult(count, centeredSumXY, centeredSumX2, centeredSumY2, sumXYdiff2);
}
else
{
result = computeResult(count, sumXY, sumX2, sumY2, sumXYdiff2);
}
if (!Double.IsNaN(result))
{
result = normalizeWeightResult(result, count, cachedNumUsers);
}
return(result);
}
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) {
var preferredItemIDsIterator = ((IEnumerable<long>)preferredItemIDs).GetEnumerator();
if (preferredItemIDs.Length > maxItems) {
double samplingRate = (double) maxItems / preferredItemIDs.Length;
log.Info("preferredItemIDs.Length {0}, samplingRate {1}", preferredItemIDs.Length, samplingRate);
preferredItemIDsIterator =
new SamplinglongPrimitiveIterator(preferredItemIDsIterator, samplingRate);
}
FastIDSet possibleItemsIDs = new FastIDSet();
while (preferredItemIDsIterator.MoveNext()) {
long itemID = preferredItemIDsIterator.Current;
IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID);
int prefsLength = prefs.Length();
if (prefsLength > maxUsersPerItem) {
var sampledPrefs =
new FixedSizeSamplingIterator<IPreference>(maxUsersPerItem, prefs.GetEnumerator());
while (sampledPrefs.MoveNext()) {
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(sampledPrefs.Current.GetUserID()));
}
} else {
for (int i = 0; i < prefsLength; i++) {
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(prefs.GetUserID(i)));
}
}
}
possibleItemsIDs.RemoveAll(preferredItemIDs);
return possibleItemsIDs;
}
public override Factorization Factorize()
{
log.Info("starting to compute the factorization...");
Features features = new Features(this);
/// feature maps necessary for solving for implicit feedback
IDictionary <int, double[]> userY = null;
IDictionary <int, double[]> itemY = null;
if (usesImplicitFeedback)
{
userY = userFeaturesMapping(dataModel.GetUserIDs(), dataModel.GetNumUsers(), features.getU());
itemY = itemFeaturesMapping(dataModel.GetItemIDs(), dataModel.GetNumItems(), features.getM());
}
IList <Task> tasks;
for (int iteration = 0; iteration < numIterations; iteration++)
{
log.Info("iteration {0}", iteration);
/// fix M - compute U
tasks = new List <Task>();
var userIDsIterator = dataModel.GetUserIDs();
try {
ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, itemY) : null;
while (userIDsIterator.MoveNext())
{
long userID = userIDsIterator.Current;
var itemIDsFromUser = dataModel.GetItemIDsFromUser(userID).GetEnumerator();
IPreferenceArray userPrefs = dataModel.GetPreferencesFromUser(userID);
tasks.Add(Task.Factory.StartNew(() => {
List <double[]> featureVectors = new List <double[]>();
while (itemIDsFromUser.MoveNext())
{
long itemID = itemIDsFromUser.Current;
featureVectors.Add(features.getItemFeatureColumn(itemIndex(itemID)));
}
var userFeatures = usesImplicitFeedback
? implicitFeedbackSolver.solve(sparseUserRatingVector(userPrefs))
: AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(userPrefs), lambda, numFeatures);
features.setFeatureColumnInU(userIndex(userID), userFeatures);
}
));
}
} finally {
// queue.shutdown();
try {
Task.WaitAll(tasks.ToArray(), 1000 * dataModel.GetNumUsers());
} catch (AggregateException e) {
log.Warn("Error when computing user features", e);
throw e;
}
}
/// fix U - compute M
//queue = createQueue();
tasks = new List <Task>();
var itemIDsIterator = dataModel.GetItemIDs();
try {
ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, userY) : null;
while (itemIDsIterator.MoveNext())
{
long itemID = itemIDsIterator.Current;
IPreferenceArray itemPrefs = dataModel.GetPreferencesForItem(itemID);
tasks.Add(Task.Factory.StartNew(() => {
var featureVectors = new List <double[]>();
foreach (IPreference pref in itemPrefs)
{
long userID = pref.GetUserID();
featureVectors.Add(features.getUserFeatureColumn(userIndex(userID)));
}
var itemFeatures = usesImplicitFeedback
? implicitFeedbackSolver.solve(sparseItemRatingVector(itemPrefs))
: AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(itemPrefs), lambda, numFeatures);
features.setFeatureColumnInM(itemIndex(itemID), itemFeatures);
}));
}
} finally {
try {
Task.WaitAll(tasks.ToArray(), 1000 * dataModel.GetNumItems());
//queue.awaitTermination(dataModel.getNumItems(), TimeUnit.SECONDS);
} catch (AggregateException e) {
log.Warn("Error when computing item features", e);
throw e;
}
}
}
log.Info("finished computation of the factorization...");
return(createFactorization(features.getU(), features.getM()));
}
public override IPreferenceArray GetPreferencesForItem(long itemID)
{
return(_delegate.GetPreferencesForItem(itemID));
}
